© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 10505
    Prev
    Next
    INDEX
    Explanations

    references to time, particularly instances of the word "last" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.72
     ModelExpression
    -0.67
     AssemblyCulture
    -0.66
     therewith
    -0.66
    Портал
    -0.63
    ัติ
    -0.62
    Palmarès
    -0.61
    Hasil
    -0.60
     autorytatywna
    -0.60
     adjoint
    -0.60
    POSITIVE LOGITS
     last
    0.91
     slightly
    0.81
     previous
    0.79
     sufficiently
    0.76
     ultimi
    0.73
     Slightly
    0.73
     somewhat
    0.72
     afgelopen
    0.72
    slightly
    0.71
     relatively
    0.69
    Activations Density 0.178%

    No Known Activations